Learning Modes

Control when and how agents learn.

Learning modes control when and how a Learning Machine captures information. Each store can use a different mode.

Mode	How it works	Tradeoff
Always	Extraction runs automatically after each response	Extra LLM call per interaction
Agentic	Agent receives tools and decides what to save	May miss implicit information
Propose	Agent proposes learnings, user confirms before saving	Requires user interaction

Always Mode

Extraction happens automatically in the background. No agent tools involved.

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.learn import LearningMachine, LearningMode, UserProfileConfig
from agno.models.openai import OpenAIResponses

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"),
    learning=LearningMachine(
        user_profile=UserProfileConfig(mode=LearningMode.ALWAYS),
    ),
)

# Profile info extracted automatically - no tool calls visible
agent.print_response(
    "I'm Alice Chen, but please call me Ali.",
    user_id="[e-mail]",
)

Best for: User Profile, User Memory, Session Context

Agentic Mode

The agent receives tools and decides when to save.

from agno.learn import LearningMachine, LearningMode, UserProfileConfig

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=LearningMachine(
        user_profile=UserProfileConfig(mode=LearningMode.AGENTIC),
    ),
)

# Agent decides to call update_user_profile tool
agent.print_response(
    "Remember that I prefer dark mode interfaces.",
    user_id="[e-mail]",
)

Best for: Learned Knowledge, Entity Memory, Decision Log

Tools by Store

Store	Tools
User Profile	update_user_profile
User Memory	save_user_memory, delete_user_memory
Entity Memory	search_entities, create_entity, update_entity, add_fact, add_event
Learned Knowledge	search_learnings, save_learning
Decision Log	log_decision, record_outcome, search_decisions

Propose Mode

The agent proposes learnings. User must confirm before saving.

from agno.learn import LearningMachine, LearningMode, LearnedKnowledgeConfig

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=LearningMachine(
        knowledge=knowledge,
        learned_knowledge=LearnedKnowledgeConfig(mode=LearningMode.PROPOSE),
    ),
)

# Agent proposes, user confirms
agent.print_response(
    "That's a great insight about API rate limits - we should remember that.",
    user_id="[e-mail]",
)

Best for: High-stakes knowledge, regulated environments, quality control

Combining Modes

Use different modes for different stores:

from agno.learn import (
    LearningMachine,
    LearningMode,
    UserProfileConfig,
    UserMemoryConfig,
    LearnedKnowledgeConfig,
)

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=LearningMachine(
        user_profile=UserProfileConfig(mode=LearningMode.ALWAYS),     # Automatic
        user_memory=UserMemoryConfig(mode=LearningMode.ALWAYS),       # Automatic
        learned_knowledge=LearnedKnowledgeConfig(mode=LearningMode.AGENTIC),  # Agent-driven
    ),
)

Defaults by Store

Store	Default mode	Reason
User Profile	Always	Names and preferences should be captured consistently
User Memory	Always	Observations accumulate passively
Session Context	Always	Session state needs continuous tracking
Entity Memory	Agentic	Agent builds knowledge graph as needed
Learned Knowledge	Agentic	Agent decides what insights are worth saving
Decision Log	Agentic	Agent logs significant decisions explicitly

Choosing a Mode

Scenario	Mode
Capture user names and preferences	Always
Build user memory automatically	Always
Track session progress	Always
Agent-driven knowledge capture	Agentic
Build entity knowledge graphs	Agentic
Audit agent decisions	Agentic
High-value collective knowledge	Propose
Compliance-sensitive learning	Propose